Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The news felt like a physical blow. Standing in the doorway, Sam watched as Chloe recounted her plans for a move to Colorado. His world seemed to shrink, as the realization of her leaving washed over him. He felt a prickle of goosebumps, despite the warmth of the summer air.

He fumbled for a response, but his mind was a blank slate. He felt a sudden, inexplicable urge to do something, anything, to stop time, to prevent this inevitable change. He took a hesitant step toward her, then stopped, his hands clenching at his sides.

The light from the setting sun seemed to paint her in a golden hue, as if she were already fading. He blinked hard, trying to hold back the sudden sting behind his eyes. He focused on the details around him, the cracked pavement, the buzzing of the cicadas, trying to ground himself in the moment, to find a way to deal with the inevitable.

Emotion: awestruck

Cluster: Surprise / Confusion
PC1 (Valence): -0.17 Negative
PC2 (Disposition): -1.20

Role in Research

This story is one of 1,000 stories generated for the emotion awestruck. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 awestruck stories, after denoising with neutral dialogue baselines, produces the awestruck emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the awestruck vector is projected through the unembedding matrix.

Promoted:
L0.271
suddenly0.260
stranger0.252
plötzlich0.246
wonder0.242
Suppressed:
la-0.450
싶-0.350
K-0.319
rest-0.248
싶은-0.238